Model comparison
Ministral 8B vs Qwen1.5-7B
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 28.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Ministral 8B scores higher in 5 categories and Qwen1.5-7B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-7B leads 28.7 to 12.6.
Side by side
| Ministral 8B | Qwen1.5-7B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 28.2 | 31.4 |
| Released | 2024-10-01 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 17 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Ministral 8B: 35.0 (#230), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1202 | 1107 |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Qwen1.5-7B: —
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Qwen1.5-7B leads
Ministral 8B: 18.4 (#281), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1065 |
| DTBench | 45.7% | — |
Math Qwen1.5-7B leads
Ministral 8B: 25.7 (#267), Qwen1.5-7B: 31.4 (#224)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1188 | 1080 |
| MATH Level 5 | 14.9% | — |
Knowledge Qwen1.5-7B leads
Ministral 8B: 12.6 (#297), Qwen1.5-7B: 28.7 (#243)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1170 | 1055 |
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
| MMLU | — | 62.6% |
Multilingual Ministral 8B leads
Ministral 8B: 35.1 (#247), Qwen1.5-7B: 28.5 (#271)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1165 | 1058 |
| LMArena Chinese | 1193 | 1141 |
| LMArena Russian | 1195 | 1006 |
Instruction Following Ministral 8B leads
Ministral 8B: 60.5 (#250), Qwen1.5-7B: 54.1 (#281)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1161 | 1058 |
Long Context Ministral 8B leads
Ministral 8B: 36.7 (#227), Qwen1.5-7B: 33.1 (#266)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1212 | 1090 |
Writing & Preference Ministral 8B leads
Ministral 8B: 39.6 (#246), Qwen1.5-7B: 29.6 (#293)
| Benchmark | Ministral 8B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1191 | 1083 |
| LMArena Creative Writing | 1175 | 1035 |
| LMArena Multi-Turn | 1166 | 1062 |
Frequently asked questions
Is Ministral 8B better than Qwen1.5-7B?
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 28.2 on the Noometry Index.
Is Ministral 8B or Qwen1.5-7B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 32.2 in the Noometry coding category.
How many benchmarks do Ministral 8B and Qwen1.5-7B share?
12 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Qwen1.5-7B has 13.